Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to weapons and arms-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jeffries
    -0.51
    Esti
    -0.51
     المعيارى
    -0.51
     Esti
    -0.51
    hires
    -0.50
     ?>/
    -0.48
    jumper
    -0.48
     Vist
    -0.48
    jsoup
    -0.47
     Creep
    -0.46
    POSITIVE LOGITS
     weapon
    1.38
     weapons
    1.30
     armas
    1.27
     senjata
    1.25
    Weapon
    1.25
     Weapon
    1.24
    Weapons
    1.23
     arms
    1.21
    weapon
    1.20
    weapons
    1.20
    Act Density 0.178%

    No Known Activations